Trends in AI-powered classification of thyroid neoplasms based on histopathology images, a systematic review

Abstract

Background Assessment of thyroid nodules histopathology using AI is crucial for an accurate diagnosis. This systematic review aims to analyze recent works employing deep learning approaches for classifying thyroid nodules based on histopathology images, evaluate their performance, and identify limitations. Methods Eligibility criteria focused on peer-reviewed English papers published in the last 5 years, applying deep learning to categorize thyroid histopathology images. The PubMed database was searched using relevant keywords combination. Descriptive analysis of extracted data on approaches, accuracy, and limitations. Results Out of 103 articles, 11 studies met inclusion criteria. They used convolutional neural networks (CNNs) to classify thyroid nodules. Accuracy ranged from 77% to 100%, with most over 90%. Discussion The findings from our analysis reveal the effectiveness of deep learning to identify discriminative morphological patterns from histopathology images thus leading to enhancing the accuracy of thyroid nodule histopathological classification. Key limitations were small sample sizes, subjective annotation, and limited dataset diversity. Further research with larger diverse datasets, model optimization, and real-world validation is essential to translate these tools into clinical practice.